The U.S. Air Force Test Pilot School and Defense Advanced Research Projects Agency demonstrated the ability of artificial intelligence algorithms to control the X-62A Variable Flight Stability Test Vehicle as part of DARPA's Air Warfare Evolution Program.
The military and DARPA tested an AI-controlled X-62A VISTA aircraft and a manned F-16 aircraft in a line-of-sight combat scenario, also known as a dogfight, during an Air Force Materiel demonstration at Edwards Air Force Base, California. The command made the announcement on Wednesday.
“It’s easy to look at the X-62A ACE program and think it’s under autonomous control and capable of air combat, but that’s beside the point. “All the lessons we're learning apply to any task we can give an autonomous system,” said Bill Gray, the school's lead test pilot.
This demonstration marks the first use of machine learning-based autonomy in a flight-critical platform.
“The X-62A is an excellent platform for not only advancing the state of research and testing, but also for training the next generation of test leaders,” said Col. James Valpiani, Test Pilot School commander.
In addition to the Air Force, DARPA's ACE program partners include Johns Hopkins University, MIT's Computer Science and Artificial Intelligence Laboratory, Calspan, Cubic, EpiSci, Lockheed Martin's Skunk Works division, and Shield AI.
